{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VOKHRUJGWQEBQFYJLXFSR4GIBK","short_pith_number":"pith:VOKHRUJG","canonical_record":{"source":{"id":"2503.21123","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2025-03-27T03:25:21Z","cross_cats_sorted":[],"title_canon_sha256":"d3aafb6c26edf227ed5bc94649b1887d7e2cc474fbca5e95ca22ce034fa6b813","abstract_canon_sha256":"cfe66bcdae3074132e34a7cb760e8d9279f16c303cf85f8a10062aaf36d556b0"},"schema_version":"1.0"},"canonical_sha256":"ab9478d126b4081817095dcb28f0c80ab9c80f5cae4b5343975ee167ff19c2e2","source":{"kind":"arxiv","id":"2503.21123","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.21123","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"arxiv_version","alias_value":"2503.21123v1","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21123","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"pith_short_12","alias_value":"VOKHRUJGWQEB","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"pith_short_16","alias_value":"VOKHRUJGWQEBQFYJ","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"pith_short_8","alias_value":"VOKHRUJG","created_at":"2026-07-05T10:40:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VOKHRUJGWQEBQFYJLXFSR4GIBK","target":"record","payload":{"canonical_record":{"source":{"id":"2503.21123","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2025-03-27T03:25:21Z","cross_cats_sorted":[],"title_canon_sha256":"d3aafb6c26edf227ed5bc94649b1887d7e2cc474fbca5e95ca22ce034fa6b813","abstract_canon_sha256":"cfe66bcdae3074132e34a7cb760e8d9279f16c303cf85f8a10062aaf36d556b0"},"schema_version":"1.0"},"canonical_sha256":"ab9478d126b4081817095dcb28f0c80ab9c80f5cae4b5343975ee167ff19c2e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:20.031504Z","signature_b64":"1IZq3AbrZ4+dhHUA8KCM9UxqVrEP3301q1PUl6BhBvlLAf4aE5VVIVHGlJEOceFc31mbcyz6U3ptczXURbItCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab9478d126b4081817095dcb28f0c80ab9c80f5cae4b5343975ee167ff19c2e2","last_reissued_at":"2026-07-05T10:40:20.031111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:20.031111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.21123","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:40:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rtyrBbjsxxDpsPHZ3mK6uWoI4TEzubfnMwT7tcEAt3FFzkN0r10EqhF4wYZdMrYKAAtFlVJ5xBUmhOgIf/cWAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:16:09.817034Z"},"content_sha256":"8f030b6c59ba688f205dbdcbcfd8c0bfbb6447a9a54ca5e1c66d6f529dac2d91","schema_version":"1.0","event_id":"sha256:8f030b6c59ba688f205dbdcbcfd8c0bfbb6447a9a54ca5e1c66d6f529dac2d91"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VOKHRUJGWQEBQFYJLXFSR4GIBK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"De Novo Functional Protein Sequence Generation: Overcoming Data Scarcity through Regeneration and Large Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Chenyu Ren, Daihai He, Jian Huang","submitted_at":"2025-03-27T03:25:21Z","abstract_excerpt":"Proteins are essential components of all living organisms and play a critical role in cellular survival. They have a broad range of applications, from clinical treatments to material engineering. This versatility has spurred the development of protein design, with amino acid sequence design being a crucial step in the process. Recent advancements in deep generative models have shown promise for protein sequence design. However, the scarcity of functional protein sequence data for certain types can hinder the training of these models, which often require large datasets. To address this challeng"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21123","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.21123/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:40:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d1VSKkABipY9A8xp4eVlmabv0ah7fKZqEhf1oz9cc2oUzm/bcCsOGRA9u5mW8q7WQAejbxhmYGaalu3TjgaaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:16:09.817954Z"},"content_sha256":"479077bf8daac8594323b17e201df16d51e0307efd6394b14d07809796936de4","schema_version":"1.0","event_id":"sha256:479077bf8daac8594323b17e201df16d51e0307efd6394b14d07809796936de4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VOKHRUJGWQEBQFYJLXFSR4GIBK/bundle.json","state_url":"https://pith.science/pith/VOKHRUJGWQEBQFYJLXFSR4GIBK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VOKHRUJGWQEBQFYJLXFSR4GIBK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T17:16:09Z","links":{"resolver":"https://pith.science/pith/VOKHRUJGWQEBQFYJLXFSR4GIBK","bundle":"https://pith.science/pith/VOKHRUJGWQEBQFYJLXFSR4GIBK/bundle.json","state":"https://pith.science/pith/VOKHRUJGWQEBQFYJLXFSR4GIBK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VOKHRUJGWQEBQFYJLXFSR4GIBK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VOKHRUJGWQEBQFYJLXFSR4GIBK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cfe66bcdae3074132e34a7cb760e8d9279f16c303cf85f8a10062aaf36d556b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2025-03-27T03:25:21Z","title_canon_sha256":"d3aafb6c26edf227ed5bc94649b1887d7e2cc474fbca5e95ca22ce034fa6b813"},"schema_version":"1.0","source":{"id":"2503.21123","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.21123","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"arxiv_version","alias_value":"2503.21123v1","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21123","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"pith_short_12","alias_value":"VOKHRUJGWQEB","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"pith_short_16","alias_value":"VOKHRUJGWQEBQFYJ","created_at":"2026-07-05T10:40:20Z"},{"alias_kind":"pith_short_8","alias_value":"VOKHRUJG","created_at":"2026-07-05T10:40:20Z"}],"graph_snapshots":[{"event_id":"sha256:479077bf8daac8594323b17e201df16d51e0307efd6394b14d07809796936de4","target":"graph","created_at":"2026-07-05T10:40:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.21123/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Proteins are essential components of all living organisms and play a critical role in cellular survival. They have a broad range of applications, from clinical treatments to material engineering. This versatility has spurred the development of protein design, with amino acid sequence design being a crucial step in the process. Recent advancements in deep generative models have shown promise for protein sequence design. However, the scarcity of functional protein sequence data for certain types can hinder the training of these models, which often require large datasets. To address this challeng","authors_text":"Chenyu Ren, Daihai He, Jian Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2025-03-27T03:25:21Z","title":"De Novo Functional Protein Sequence Generation: Overcoming Data Scarcity through Regeneration and Large Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21123","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8f030b6c59ba688f205dbdcbcfd8c0bfbb6447a9a54ca5e1c66d6f529dac2d91","target":"record","created_at":"2026-07-05T10:40:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cfe66bcdae3074132e34a7cb760e8d9279f16c303cf85f8a10062aaf36d556b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2025-03-27T03:25:21Z","title_canon_sha256":"d3aafb6c26edf227ed5bc94649b1887d7e2cc474fbca5e95ca22ce034fa6b813"},"schema_version":"1.0","source":{"id":"2503.21123","kind":"arxiv","version":1}},"canonical_sha256":"ab9478d126b4081817095dcb28f0c80ab9c80f5cae4b5343975ee167ff19c2e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab9478d126b4081817095dcb28f0c80ab9c80f5cae4b5343975ee167ff19c2e2","first_computed_at":"2026-07-05T10:40:20.031111Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:20.031111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1IZq3AbrZ4+dhHUA8KCM9UxqVrEP3301q1PUl6BhBvlLAf4aE5VVIVHGlJEOceFc31mbcyz6U3ptczXURbItCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:20.031504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.21123","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f030b6c59ba688f205dbdcbcfd8c0bfbb6447a9a54ca5e1c66d6f529dac2d91","sha256:479077bf8daac8594323b17e201df16d51e0307efd6394b14d07809796936de4"],"state_sha256":"c026bc38d0131523bc65eb7327b252c53b492fd4370e152bbf3471ca323c0f97"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dsvL/fRZm5c2bZvkOKUPnZjaX0L0VoUzCc+zNFb3zCVeVAaqD2J1A8v6Uat40BhGnOMRChqcRMR+ntq2vKxvDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:16:09.823701Z","bundle_sha256":"1889e211b11943159f8e618bba5b3851838cbc424a4383ad562f600e94c8087b"}}